No. 2 (2022)

An immunological model of clonal selection with positive selection based on the principles
of mass-parallel data processing used in artificial immune systems, is proposed. The model is
designed for text-independent identification of a person by voice. In contrast to known passwordbased
voice identification systems, the proposed model implements decentralized recognition of
voice data by matching it with detectors that simulate immunocompetent cells of the immune system.
The initial voice features are generated in a linear speech predictor and are represented by
cepstral coefficients. The sequence of cepstral coefficients is further divided into equal time sections
- morphemes, which are abstract linguistic units that unify phonemes. Morphemes carry the
individual coloring of consecutive temporal segments of speech reproduced by the voice, allowingthem to be used productively as voice identifiers. The matching of voice morphemes with detectors
is carried out according to the principle of positive selection based on the Euclidean proximity
measure. The model's "friend-or-foe" identification decision making is implemented on the basis of
a statistical approach in terms of the frequency of detector response. The proposed model implements
the identification of the speaker's personality at the rate of receipt of his voice data. At the
same time, personality identification is invariant to the language, volume and content of speech.
The advantage of the model is complete protection against replay attacks. The effective realization
of the model, the accuracy and speed of identification are due to the possibility of organizing highspeed
analysis of large volumes of voice data, which in the long term corresponds to the pace of
development and application of high-performance computing systems.

The paper discusses optimization methods that are based on processes occurring in nature. Such
methods have become increasingly used to solve complex problems. However, such methods have some
drawbacks, which stimulates the development of new and more advanced optimization methods. Solving
NP complete problems requires optimal methods that will meet all design requirements, so there is a
need to develop new and more advanced methods for solving this class of problems. As such a method,
the authors propose an optimization method based on a model of the behavior of stem cells in the natural
environment. The conducted studies of the proposed method provide solutions that can overcome
many of the shortcomings of standard optimization approaches, such as getting into the local optimum
or low convergence rate of the algorithm based on the method under consideration. The purpose of this
work is to develop an optimization method and an algorithm based on it for solving a complex objective
function. The scientific novelty lies in the development of an optimization method based on the stem cell
behavior model for solving NP complete problems. The aim of the work is to create conditions for theoptimal search for a solution to complex functions by applying the search method and, based on it, an
algorithm for the behavior of stem cells. The practical value of the work lies in the development of a new
metaheuristic optimization method for the efficient solution of NP complete problems. Also in the work,
a comparative analysis with well-known competitors was carried out. The main difference of the proposed
method from other known methods is the use of a new approach of bioinspired search based on
the behavior of stem cells, which, as shown by practical comparison, has an advantage over known
analogues. The results of a practical comparison of methods and algorithms based on them showed the
advantages of the approach proposed in the work on known test functions. After analyzing the problem
of creating methods, algorithms and software for solving NP complete problems, we can conclude that
the development of such approaches is currently an urgent task.

In this paper the planning and scheduling problem as an important optimization problem in
many transportation and robotic applications is discussed. To solve planning problems, the main
approaches are based on optimization methods, sampling-based methods, and usually such kinds
of problems are NP-hard and high dimensional. In this work, the method for planning and scheduling
based on the fuzzy finite state machine model is developed. Fuzzy graph presentation of the
scheduling problem and operation planning is given. The paper presents two approaches to the
formulation of the planning problem with limited resources and temporal variables: state-oriented
(with transitions between states), temporal ordering-oriented (on a time scale). Temporal modeling
for planning problems implies a qualitative approach to managing the distribution of operations
or topological ordering, as well as a quantitative approach to handling imprecise durationsrelationships between operations in multiple parameters. The concepts of fuzzy intervals and fuzzy
relations are introduced for planning operations on a graph. A planning algorithm based on the
theory of automata and temporal modeling under uncertainty has been developed. Using this formalism,
a path planning problem is solved by successively altering a state using various operations
until a solution is found. The idea of temporal-ordered partial schedule associated with the
planning state of the system is discussed. A model of a finite automaton for a planning system under
conditions of uncertainty is proposed. A method and algorithm for scheduling operations
based on a non-deterministic finite automaton and an enumeration scheme have been developed.
The non-deterministic computation for a scheduling problem is a decision tree whose root corresponds
to the beginning of the scheduling process, and each branch point in the tree corresponds
to a computation point at which the machine has multiple choices. And the finite state machine
model (automata) for the planning system under uncertainty is suggested.

The article is devoted to the research of the assessment of influencing factors and forecasting
of power consumption in the regional power system, taking into account its operating modes.
The analysis of existing methods of forecasting energy consumption is carried out. The choice of a
forecasting method using an artificial neural network is justified. An algorithm for creating a neural
network for short-term prediction of electrical load is considered. The relevance of the work is
due to the requirements of the current legislation for forecasting electricity consumption in order
to solve the problem of maintaining a balance of power between the generating side and the consumption
of electric energy. At the same time, one of the main tasks related to the generation of
electric energy and its consumption is the task of maintaining a balance of capacities. On the one
hand, with an increase in the planned load, interruptions in the supply of electricity may occur, on
the other hand, a decrease in electricity consumption will also lead to a decrease in the efficiency
of power plants, and ultimately to an increase in the cost of electricity both for the wholesale electricity
market and for the end user. The developed neural network model reduces the task of shortterm
forecasting of power consumption to the search for a matrix of free coefficients by training
on available statistical data (active and re-active power, ambient temperature, date and index of
the day). The received NS model of short-term forecasting of power consumption of a section of
the district 10 kV electric grid takes into account the factors: – time, - meteorological conditions,
– disconnections of individual power supply lines of cottages, – operating mode of electricity consumers.
Predictive estimates of the power consumption of the power system have been obtained
based on the data of the electricity consumed by the outdoor temperature, the type of day, etc. The
model for predicting the magnitude of the consumed active and reactive power is quite workable,
but at this stage still has a fairly high level of forecasting error. To improve the accuracy of forecasting,
it is necessary to increase the database that makes up the training sample, because at the
moment the available data cover a time period of only 3–4 months. The results of the analysis
showed that forecasting reactive power consumption causes the greatest difficulties.

The paper has devoted to the research and automation of mathematical modeling of the process
of heating the elements of the thin-walled aluminum waveguide path when working out the
induction soldering technological procedure. The paper has reviewed the method of mathematical
modeling of the induction soldering technological process. In order to develop the technological
process of induction soldering, an instant source of a flat rod heating is used as a mathematical
model of waveguide path heating. As part of this work, a functional automated subsystem of mathematical
modeling of the induction soldering technological process of thin-walled metal waveguides
of cosmic aircraft was designed and implemented. The functionality of the application allows
you to make an automated construction of the mathematical model of the induction soldering
technological process with specified parameters, performing calculations of the temperature values
of the part-components participating in the process of the induction soldering, depending on
the specified sizes, structural-physical and thermodynamic characteristics, the power of the inductor
and the position of the flange/couplings relative to the inductor. The obtained software product
is an optimal solution for integration with the system that produces the process of controlling the
induction soldering of the waveguide paths of spacecraft as a generator of mathematical models of
the induction soldering process for machine learning. Comparative researches of the induction
soldering models have carried out, which builds the mathematical module of the program for their
compliance with the real process in permissible limits. Experiments have conducted on a software
system for controlling the induction soldering process of the waveguide paths, including an induction
heating generator, an inductor, a manipulator, an IPPC-9171G-07BTO industrial computer
with a control console. An experimental verification of the correctness of the selected mathematical
model of the induction soldering technological process and the correctness of its implementation
in the developed software application has performed. The MSE values of the results of modeling
and real technological processes of induction soldering have calculated. As a result of attentive
and model experiments, it has established that the application of the induction heating of the
elements of thin-walled aluminum waveguide paths of cosmic aircraft with a sufficiently high accuracy
simulates this technological process.

This article considers the problem of operational planning of one-subject production.
The organization of machine-building production is a complex set of works to determine the interrelated
indicators that characterize the activities of the enterprise. Enterprises of this type have a
complex hierarchical structure. It is also necessary to take into account that when planning the
production process, the number of parameters is large and not all of them can be accurately determined,
which affects the efficiency of the enterprise. To solve the problem of effective planning,
the optimality criteria for serial one-subject production were analyzed. One-subject production
includes those where parts of the same name are processed, that is, a production line is formed.
Consequently, the task of optimizing production is to distribute the entire set of work between the
machines and operators servicing this machine in such a way that the planned task is completed
within a given time and the total cost of completing the task is minimal. The article considers the
problem of assignment under uncertainty, carried out experimental calculations and analyzed the
results obtained, which justifies the use of the proposed apparatus of fuzzy sets for solving the
problem of production planning. It is concluded that under conditions of uncertainty, when there is
no exact or statistical information, the apparatus of fuzzy sets makes it possible to analyze theeffectiveness of production activities when setting parameters that reflect the possible values of the
system. In such cases, the use of fuzzy logic mechanisms in the problems of making production
decisions will make it possible to determine optimal or close to optimal solutions.

An analytical redundancy in the automatic control system of a bypass turbojet engine
(ACS turbofan engine) based on optimal observers is proposed. This article is based on previously
obtained results in previous author's works and is a generalization and analysis of these results in
order to develop a methodology for improving the fault tolerance of ACS turbofan engines. This
method is based on the use of optimal observers: the Kalman filter and the Yazvinsky filter, consistent
with the mathematical model of the ACS turbofan engine. The analysis of the mathematical model of
the ACS was carried out using the least squares method in a moving window. The accuracy of identification
of the mathematical model and the required delay time are ensured by optimizing the width
of the moving window. Estimated with the help of optimal observers, the output vector of the ACS
turbofan engine includes the following parameters: the rotor speed of the low-pressure compressor
rotor nв, the rotor speed of the high-pressure compressor nk, the air pressure behind the highpressure
compressor PK, the gas temperature behind the low-pressure turbine TT. When modeling the
Kalman filter, a correlation analysis of the input signals was preliminarily carried out. The rationale
for the advantage of the adaptive Yazvinsky filter compared to the Kalman filter is given. The results
of mathematical modeling of the algorithmic method of reserving the measurement channel of the
ACS turbofan engine based on the data of flight tests of a bypass engine of the PS-90A type as part of
the main narrow-body aircraft TU-214 both in stationary and transient modes are presented. Statistical
analysis of errors in estimation of the output vector of ACS turbofan engines based on the Kalman
and Yazvinsky filter has been carried out. It is shown that the proposed analytical redundancy algorithm
ensures the fulfillment of the requirements for the accuracy and stability of estimates of the
output vector of ACS turbofan engines when using the Yazvinsky filter and can be recommended for
use in advanced ACS turbofan engines. Based on the results proposed redundancy method, a direction
for further research has been formed.

The rapid development of "multi-agent systems" as an independent and multifaceted section
of artificial intelligence attracts many researchers in various fields of activity. The pace of progress
in the development of information technologies, distributed information systems, and computer
technology determines the possibilities of using robotics technologies in the Armed Forces of
the Russian Federation. The factors presented in the article authorize the need to introduce new
intelligent technologies into the troops - autonomous robotic complexes (systems). The development
of artificial intelligence methods makes it possible to take a new step towards changing the
style of interaction of complexes with each other as part of a robotic system. The idea of creating
so-called "autonomous complexes" arose, which gave rise to a new style of adaptive group management.
Instead of interaction initiated by the user-operator through commands and direct manipulations,
complexes are independently involved in the joint process of solving a common problem
in a non-deterministic dynamic environment. The article proposes a formalized approach to
the design of architectures for group interaction of autonomous robotic complexes in a system
based on the law of open control, i.e. induced and reliable preferences of each complex for action,
satisfying the conditions of perfect coordination of their activities, by identifying parameters at
which the objective function is maximized in various modes of functioning of the robotic system. A
formalized formulation of the problem of synthesis of the adaptive group control system of autonomous
robotic complexes under conditions of a priori uncertainty is presented. The architecture of
group interaction of complexes is adaptively built based on the conditions of the external environment
and the internal state of the system, in which each complex of the group functions to achieve
a common goal (solving a system problem) at the time under consideration.

Autogenerators have found wide application in the receiving and transmitting equipment of
communication, navigation and radar, as they determine their stability, power and other important
parameters. The object of research in this work is a 1.5 GHz heterodyne from the C4-60 spectrum
analyzer. Since the technical description of this device does not contain a number of important
parameters, the purpose of the study is to study the frequency run-out, the frequency dependence
on the supply voltage, the harmonic level. A schematic diagram and a brief description of the generator
design are given. The simulation of a coaxial resonator in the Microwave Office package is
carried out. The amplitude-frequency characteristic of the resonator is given. The results of an
experimental study of a 1.5 GHz autogenerator are presented. The estimation of parasitic parameters
in the spectrum of the output signal is given. The frequency run-out and modulation characteristic
along the power supply circuit were measured. These data allow us to make a reasonable
requirement for the stability of the supply voltage. The results obtained can be used in the design
of receiving and transmitting communication equipment, navigation, electronic warfare. The article
may be useful for students and teachers of educational institutions in the educational design ofreceiving and transmitting equipment. The following electrical parameters have been achieved:
– operating frequency 1500 ±1.5 MHz; – output power of at least 13 dBm; – supply voltage minus
12.6 V; – consumption current no more than 60 mA; – frequency run-out in 24 minutes after
switching on no more than 325 kHz; – frequency departure when the voltage changes from minus
5 V to minus 13 V no more than 241 kHz.

In the 80s of the last century, integrated injection logic (I2L) was widely used as an element
base. Somewhat later, injection-field logic (IPL) appeared in the development of I2L capabilities
for building VLSI. Thanks to the use of a field-effect transistor as a key element of the inverter, in
this element basis it was possible to significantly reduce an important indicator for VLSI – power
consumption - reaching the peak-watt range. An even greater reduction in power consumption can
be achieved by using two field-effect transistors in the inverter unit cell, which is proposed in this
paper. This element basis is proposed to be called field-field logic, or in the future P2L. To reduce
the dimensions of the P2L cell, field-effect transistors, both key and load, are made with a vertical
channel. In addition, to ensure a positive supply voltage, an n-channel transistor is used as a key
one, and a p–channel transistor is used as a load one. Both transistors are normally closed, i.e.
closed at zero gate voltage. Topological variants of P2L-cell execution from geometry with annular
gates to geometry with linear gates proposed by the author earlier are considered. The topological
norms adopted in the consideration are the norms of 50 nm. The power consumption in this
element basis is reduced by about two times compared to the IPL, due to the fact that the current
flows through the load transistors in the inverter chain through one inverter, as well as through
the key ones. The technological process of manufacturing a P2L cell is considered, the profiles of
the distribution of impurities in depth are calculated. The manufacturing process is designed taking
into account the fact that the load p-channel transistor must be made in an insulated pocket
using full dielectric insulation technology. The technological modes of manufacturing the P2L cell
are given. The proposed design and technological variant of the P2L cell can be recommended for
the creation of VLSI with low power consumption.

The object of research is a calibrator consisting of a quartz oscillator and a diode-based
harmonic generator with charge accumulation. The aim of the study is to identify technical parameters
and characteristics of the calibrator that are absent in the literature. An experimental
study of a quartz calibrator with a frequency grid at 50 MHz has been carried out. The following
results are presented: – overrun frequency 20 minutes after switching on; – dependence of the
frequency of the first harmonic on the supply voltage; – spectrum of harmonics in the frequency
range from 0 to 1500 MHz. A schematic diagram and a brief description of the design are given. A
photo and experimental technique are presented. The calibrator is recommended for use in receivers
and spectrum analyzers to test their performance and improve tuning accuracy. The following
electrical parameters have been achieved: – frequency setting accuracy of the first harmonic
± 2.5 kHz; – power of the first harmonic 0 dBm; – non-uniformity of harmonics in the band from
0 to 1500 MHz no more than 36 dB; – run-out of the frequency of the first harmonic in 20 minutes
34 Hz; – frequency drift of the first harmonic when the supply voltage changes from 5 to 13.5 V,
no more than 288 Hz; – the width of the spectral line at the level of minus 40 dB from the maximum
is not more than 4 Hz. Comparison of the obtained results with the known ones shows a rather
large unevenness of the harmonic power in the frequency range up to 1500 MHz. Reducing
the uneven power of harmonics can be achieved in several ways: – supplement the calibrator with
a corrector of the amplitude-frequency characteristic; – increase the frequency of the first harmonic. The advantages of this calibrator are the simplicity of the circuit and design, the possibility
of repetition in the conditions of serial production, the availability of the element base, ease of
adjustment, small weight and dimensions. Using more powerful transistors, it is possible to cover
not only the decimeter, but also the centimeter wavelength range

A common problem of traditional radio communication channels - the lack of free frequencies,
noise, low bandwidth, the need to obtain a license to use the frequency, the relative ease of hacking.
Free space optical communication channels overcome these limitations, is one of the types of communication
systems that use open space to transmit information carried by light - this points to the
need for direct visibility of the transceivers. Due to the influence of various weather conditions, the
light flux is subject to atmospheric attenuation. In this paper, a method to improve the efficiency of
high-performance wireless optical communication channels in different weather conditions: clear
sky, fog, rain and snow was investigated. The existing wireless optical communication technology, a
dense multiplexing multiplexing (DWDM) system with one input and one output (SISO), was considered.
And it was proposed to improve the existing system by applying multiple input/output (MIMO).
An impact and attenuation analysis on the wireless optical network in different weather conditionswas conducted. The study was based on the use of the Optisystem simulation software toolkit, which
is used to emulate different weather conditions of attenuation in two types of systems. Models were
developed for each of the optical communication systems studied. A comparison between SISO and
MIMO systems is made in terms of quality factor under different weather conditions. The proposed
system shows promising results in terms of performance and received signal quality. The transmission
path length of the proposed system in dense fog conditions increases by 33.6%. The transmission
path length of the proposed system in heavy rain increases by 63.89%. The transmission path
length of the proposed system in heavy snow increases by 35,21%.

The systematic component of the offset voltage (Voff) of two-stage BJT and CMOS operational
amplifiers (Op-Amps) with classical architecture significantly depends on the numerical
values (difference from unity) of the current transfer coefficient (Ki≈1) of the current mirrors (CM)
used. This parameter of CM is also influenced by the Earley stress of their dominant active components.
Current JFET mirrors are today a weak link in modern JFET analog circuitry and they
are impractical to use in the structure of JFET Op-Amps. The article posed and solved the problem
of the conditions for the elimination of CM in an Op-Amps based on field-effect transistors
with a control pn-junction for the case when it is necessary to obtain a small Voff. Variants of practical
circuits of input (InS) and intermediate (IntS) stages of microelectronic operational amplifiers
based on complementary field-effect transistors with a control pn-junction (CJFET) are proposed.
Their main feature is the absence of a current mirror, which, when implemented on a
CJFET, negatively affects the main parameters of the Op-Amps in terms of the systematic component
of the offset voltage, the attenuation coefficients of the input common-mode signal, and the
suppression of noise on the power buses. In this regard, InSs and IntSs circuits are promising,
which do not use this CJFET functional unit. The circuits of Op-Amps based on the developed InSs
with an open gain of more than 80 dB and a systematic component of the offset voltage within 300
μV with low current consumption in a static mode are presented. The relevance of the performed
studies lies in the need to develop the theory of designing high-precision JFET and CJFET IPmodules
for use in structures of low-noise analog interfaces of sensors of various physical quantities,
including those operating in severe operating conditions (exposure to low temperatures and
radiation) The proposed circuits can be implemented on wide-gap semiconductors (SiC JFET,
GaN JFET or GaAs JFET).

Currently, the actual direction is the search for functional layers for various optoelectronic
devices. A promising candidate as a basis for many such structures is zinc oxide (ZnO), which
combines a number of unique optical and photoelectric properties. However, the characteristics of
ZnO thin films can vary significantly depending on the chosen synthesis method and specific production
conditions. One of the varieties of the sol-gel method suitable for the synthesis of
nanoscale films is the dip-coating method. The paper presents the results of the synthesis of thin
films of zinc oxide on glass substrates by the method of vertical drawing from ZnO alcohol sol.
The effect of the elongation rate on the structural and optical properties of synthesized ZnO films
was studied using spectral ellipsometry and spectral photometry. By the method of spectral
ellipsometry, it was found that the change in the rate of elongation significantly affects the thickness
and porosity of the synthesized zinc oxide layers. The analysis of the obtained dependence of
the film thickness on the pulling speed showed that in the vertical pulling method, the growth of
zinc oxide on glass substrates can be realized in two modes: in capillary forces mode and in drying
mode. At the same time, transmission spectra were measured for synthesized ZnO films by
spectral photometry, the analysis of which showed the effect of the elongation rate on the position
of the edge of fundamental absorption. It was found that the main cause of the resulting.

The article describes the structure, design, installation, functionality, technical parameters
of a capacitive device used in security and warning systems for the perimeters of objects, as well
as a circuit of a patented differential-capacitive sensor with two autogenerators, which is part of
the device, the probability of detecting unauthorized intrusions is calculated and estimated using
the device. The operation of the capacitive sensor is found in the transformations of the change in
the capacitance of two sensitive elements relative to the Earth, the possibility of a protective fence,
the change in frequency using autogenerators when approaching or touching them on external
faces, and the principle of operation of the capacitive device is based on detecting detection when
the frequency difference of the autogenerators exceeds the set limit value. The advantage of
autogenerators circuits built on logic elements in a differential capacitive sensor is shown, to the
inputs of which sensitive elements are connected, one of which is used as a signal, and the other as
a reference generator. It is shown that when RLC-elements with lumped parameters and quartz
resonators are not used as frequency counters, the circuits of self-oscillators built on digital
microcircuits according to the same scheme and their adaptation to changes in the external
environment are greatly simplified. happens automatically. To transfer the high frequency signals
of the generators to the laptop, first these signals are converted into low frequency signals throughfrequency dividers, which are in the frequency counters, then these low frequency signals are
converted into digital signals using the Arduino Uno module. The software written on the laptop
calculates the frequency difference and generates an alarm at a certain value of the difference.
According to the calculations, a rather high probability of detecting unauthorized intrusions on
objects and the efficiency of using a security warning device with a differential capacitive sensor
based on two self-oscillators in the aviation security system were noted.

The most well-known beamforming device (DOU) (for linear and flat MAR) is the Rothman
lens, which is of great interest because it allows you to form a fan of MAR rays in a wide spatial
sector of angles (wide-angle scanning), has a fairly high efficiency and MAR with a lens Rothman
has a low level of side lobes. Another advantage of the MAR with a Rothman lens is the weak dependence
of the position of the rays in space on frequency, in contrast to the MAR with a Butler
matrix DOE, in which, at a high efficiency (theoretically 100%), the position of the rays depends
on the frequency. However, the previously developed analogs of the Rothman lens are large and
require additional components in the design, which affects the transmission coefficient of the lens
in the operating frequency range from 2 GHz to 20 GHz and the consistency of the device with
other components of the transceiver equipment. It follows that the study and modernization of lens
structures in relation to multibeam antenna arrays (MAR) is a topical topic for research. The purpose
of the work is to propose a method for calculating the Rotman lens, modernize the lens design,
make a lens model and conduct an experimental study of the lens in order to obtain constructive
methods for optimizing the characteristics of the Rotman lenses for use in MAP in the frequency
range from 2 GHz to 20 GHz. In the results of the article, the dimensions of the lens, the
mass of the lens, the transmission coefficient, and the simplicity of the design are estimated incomparison with the previously developed analogues. A technique for calculating the geometry of
a Rotman lens is proposed, the SWR of a printed Rotman lens is experimentally studied on a vector
network analyzer, constructive methods are obtained for optimizing the characteristics of Rotman
lenses for use in multibeam antenna arrays. A model of a broadband Rotman lens in microstrip
design with a maximum SWR of 1.3 (S21) in the operating frequency range from 2 to 20 GHz was
made, the lens size was 150x100, and the lens weight was 0.4 kg. According to these parameters,
the Rothman lens surpasses the analogues developed earlier.

The decision algorithm is the preferred filtering algorithm in data mining technology, and
its results are usually chosen in the form of "if-then" rules. Algorithm C4.5 is one of the decision
algorithms that takes advantage of the ease of understanding and increasing importance, and also
takes advantage of the advanced information rate gain of its advanced ID3 algorithm. After the
theoretical analysis of the information, the algorithm C4.5 is selected to analyze the results of
performance appraisal, and enterprise performance appraisal decisions by collecting data, preprocessing
data, calculating information gain and determining selection parameters. The system isdeveloped in B/S architecture, an R&D project management platform that can perform evaluation
analysis with decision analysis results evaluation tools and web coverage. The system includes
information storage, task management, reporting, receipt and presentation control, information
visualization and other functions of the management information system functions. They can realize
project management functions, such as creating and managing a project, flow tasks, filling and
managing information about functions, creating a performance evaluation system, creating reports
of various sizes, building management. decision decision algorithm as the core technology,
the system acquires scientific significant project management information with high data accuracy,
and realizes visualization, which can help the enterprise to have a good management system in
large areas. Task management, reporting, audit control, information visualization and other functions
of the system's management reporting management functions are included.

The use of artificial intelligence methods in the field of medicine has become widespread,
helping to diagnose, analyze and make recommendations for treatment. Psychiatry is a branch of
medicine that studies mental disorders, methods for their diagnosis and treatment. Her range of
tasks includes not only diagnosis and treatment, but also observation, monitoring and subsequent
rehabilitation of patients. This subject area has significant problems, such as objectivity, inconsistency
in the diagnosis, the complexity of the classification of diseases, and the unpredictability
of the course of the disease. With a number of these problems, the use of machine learning methods
and artificial intelligence algorithms helps to cope. This paper is devoted to a review of research
on artificial intelligence methods used to solve problems in the field of psychiatry.
The relevance of the topic is due to the high need for improvements in this subject area. Specific
issues are presented in this article. Among them, the main directions were identified: data deidentification,
classification of symptom severity, accuracy of condition prediction. To solve them,
the authors used such methods as latent semantic analysis for natural language processing, classification
methods, convolutional neural networks for prediction, and cognitive modeling. Separately,
the effectiveness of hybrid systems, including the implementation of several machine learning
methods at once, is noted. The aim of the study was to highlight the main directions of development
of research in the scientific community, which demonstrate the successful integration of artificial intelligence into psychiatry, as well as to compare them with each other according to the
obtained estimates of the accuracy of the models. Which, in turn, implies the analysis and analysis
of specific algorithms, their performance for specific tasks

The analysis of approaches based on deep learning (DL) to natural language processing
(NLP) tasks is presented. The study covers various NLP tasks implemented using artificial neural
networks (ANNs), convolutional neural networks (CNNs) and recurrent neural networks (RNNs).
These architectures allow solving a wide range of natural language processing tasks that previously
could not be effectively solved: sentence modeling, semantic role labeling, named entity
recognition, answers to questions, text categorization, machine translation. Along with the advantages
of using CNN to solve NLP problems, there are problems associated with a large number
of variable network parameters and the choice of its architecture. We propose an evolutionary
algorithm for optimizing the architecture of convolutional neural networks. The algorithm initializes
a random population of a small number of agents (no more than 5) and uses the fitness function
to get estimates of each agent in the population. Then a tournament selection is carried out
between all agents and a crossover operator is applied between the selected agents. The algorithm
has such an advantage as the small size of the network population, it uses several types of CNN
layers: convolutional layer, maximum pooling layer (subdiscretization), medium pooling layer and
fully connected layer. The algorithm was tested on a local computer with an ASUS Cerberus Ge-
Force ® GTX 1050 Ti OC Edition 4 GB GDDR5, 8 GB of RAM and an Intel(R) Core(TM) i5-4670
processor. The experimental results showed that the proposed neuroevolutionary approach is able
to quickly find an optimized CNN architecture for a given data set with an acceptable accuracy
value. It took about 1 hour to complete the algorithm execution. The popular TensorFlow framework
was used to create and train CNN. To evaluate the algorithm, public datasets were used:
MNIST and MNIST-RB. The kits contained black-and-white images of handwritten letters and
numbers with 50,000 training samples and 10,000 test samples.

This article describes the information and software for the implementation of various methods
for verifying the state of fragments of biological objects using computed tomographic images by the
decision support subsystem for the diagnosis of diseases. It is pointed out the current state of development
of medical diagnostic equipment, the equipment of which medical institutions of the country
and its non-operational accessibility to the population contributed to and led to the emergence and
active development of new directions in the field of radiation diagnostics, which include: digital and
film radiography, computed tomography, magnetic resonance imaging. The article focuses on the
analysis of X-ray images, decision-making based on the analysis of these images, diagnosis based on
the decisions made. The advantages and disadvantages of radiography as a modern diagnostic method
are analyzed relative to their analogues. An important task in the analysis of radiographic images
of medical biological objects and their fragments is to solve the problem of image quality improvement.
In order to improve the quality of X-ray images and increase their informativeness, an algorithm
has been developed and the software of the software subsystem of the medical automated information
system for their correction and analysis has been implemented. The article discusses the
implementation of solving problems of diagnosis of diseases, such as: analysis of radiographic images,
decision-making based on the analysis of these images, diagnosis based on the decisions made by
developing and applying software and information support for the implementation of methods for
verifying the state of fragments of biological objects as effective methods for diagnosing the state of
paranasal sinuses by their radiographic and computed tomographic images. The main methods underlying
verification by X-ray and computed tomography images are described. A detailed analysis
of the implementation of mathematical models of diagnostic methods in the form of algorithms implemented
by software for the functioning of the decision support subsystem of a medical automated
information system is given. Examples of practical implementation of software and information support
for verification methods of medical objects in the form of screen forms for working with fragments
of the object under study and the results of the analysis of radiographic images are shown.
This makes it possible to increase the efficiency, accuracy of verification of the state of medical biological
objects, the reliability of the disease diagnosis process. The scientific novelty, the results of
the approbation of the material presented in the article at international, All-Russian conferences,
scientific journals are shown.

Biometric identification and access control systems contain methods for recognizing a subject's
personality based on his unique physiological and behavioral characteristics. The purpose of
this work is to develop a system for secure interaction (authentication) of participants in gamified
educational projects, which includes countering security threats that arise when using biometric user
characteristics. A comparative analysis of the efficiency of recognition of fake biometric samples by
liveness detection methods based on the detection of sample substitution using a photo, video on a
display, a 3D model, and a mask has been performed. During research a method of using the liveness
detection for include to a gamified educational environment system was proposed. A modification of
the liveness detection method (hybrid method) has been proposed and a biometric identification system
in real time has been designed using the proposed method. A two-stage hybrid biometric identification
method has been developed based on the joint use of passive and active software methods for
detecting fake biometric samples. The method is adapted for use with a minimum number of additional
devices, the only biometric feature scanner is a 2D-camera. The network of types two-layer
perceptron, three-layer perceptron and convolutional neural network was tested. The network was
trained on the author's training examples. The position of the announcer when recording training
examples: the distance of the face from the camera is 60cm, the recording modes when the head is
turned by 0 (look directly into the camera), 30 (the head is slightly turned to the side) and 45 (the
head is turned strongly to the side) degrees. Based on the testing results, the best recognition rates
were found in a convolutional neural network with 3 convolutional layers and 1 fully connected one.
Accuracy of recognition of the spoken word is obtained up to 100% when the user's head is turned up
to 30° and up to 70% - when the user's head is turned up to 45°. The FAR value of this system was
1%, the FRR value was 0% for testing on 1000 samples.

The traditionally used way to assess the quality of the solution proposed by an intelligent
system is to explain the course of logical inference. Knowledge about reasoning is used to argue
the choice of a solution option. The sequence of applied rules, the facts used and the confirmed
hypotheses are considered arguments that should convince the user of the validity of the formed
conclusion. The disadvantage of this method of explanation is that it reflects a formally correct,
but devoid of semantic content, course of reasoning. The argumentation of the solution obtained is
based on the tracing protocol, which is essentially no different from debugging information when
tracing programs. The argumentation in this case is far from the meaning of the situation. The
meaning is understood as a given set of transformations of the situation that preserve the immutability
of its perception by a human analyst. Knowledge about the semantic content of situations
should be presented in a special fashion. In this paper, we consider a representation containing a
precent and its permissible transformations. In this form, spatial situations in geoinformation systems
are described. For argumentation, it is proposed to use special relations between images of
situations. The concept of the area of applicability of the image is introduced. The mutual arrangement of the spatial-temporal and semantic shell of images and the areas of their applicability
is considered as a carrier of the relationship. Information about relationships is extracted from the
structure of the cartographic database. The relations of inheritance, aggregation, composition,
generalization and association of classes of objects are considered. Knowledge for argumentation
is provided by the rules for determining the reliability index of expert conclusion for individual
relationships and their combinations. A method of automatic rule generation is proposed.
The relations for comparison of levels of reliability of rules are given.

Currently, due to widespread computerization, the development of automated control systems
is relevant. Due to the development of small businesses, the purchase of commercially available
systems is a very expensive solution. It is possible to create similar control systems based on
inexpensive microprocessor kits (in this particular case, the K1816VE35 microprocessor kit is
used). In the future, such a system will not be difficult to improve, and it is also easy to implementinterfacing with various electronic computers (control from a personal computer). A system for
measuring and regulating bulk raw materials (an automated weighing system) is to be developed,
which provides control of the pneumatic transport automation with a 2-speed rotary dispenser,
through which bulk raw materials are fed to a weighing hopper suspended on a load-bearing device.
Measuring the weight of the bulk mass in the hopper of the scales, followed by automatic
control of unloading of bulk raw materials from the hopper. The profitability of any industrial
operation involving the weighing of raw materials, work in progress and finished products directly
depends on the accuracy of the weight data. However, even when using high-precision weighing
equipment, the method of collecting, recording and processing weight data for the micro ingredients
system may be subject to errors and inaccuracies. This can cause a potential revenue drain
that is difficult to detect and verify. In many cases, it is assumed that the cause of the problem is
related to the weighing equipment, whereas in fact it is related to the traditional data collection
and management system. In many factories where bulk products are mixed in batches, dosing
scales is a manual, time-consuming operation in which the ingredients are weighed separately
before loading into a blender or other technological container. A significant number of such plants
can benefit from the installation of an automated weighing and dosing system.

The article presents the development results of a module for the retail network mobile application
modernization. A feature of the presented mobile application module is the display of personalized
messages with advertising and promotions of the retail network. A mathematical model
of machine learning is used to collect and analyze data in a mobile application. The process ofchoosing a mathematical model, the operation algorithm and the model training stages on training
data are described in detail. The quality of the classifier's work was evaluated on a test and training
sample. Test sample objects classification and the real value of the class comparison with the resulting
classification were performed. The authors in the article presented the main stages of the algorithms
development for processing statistical data from customer receipts. The program codes for the
receipt analysis module implementation and display the mobile application personalized advertising
are presented. To implement the database as a tool, the authors used the relational data management
system MS SQL Server. The modules of the mobile application are developed in the Android Studio
environment for the Android operating system family. The authors presented the algorithm main
stages and testing the implemented modules operability in the paper. Based on the data on purchases
made by the buyer, information about preferred products is collected based on the fixation of product
groups and product items from the receipt. The loyalty card of the retail network is linked to the mobile
application, and receipts for purchases are linked to loyalty cards, in turn. Previously, the application
displayed ads for all products participating in promotions. The actual task is to display personalized
advertising, which has proven its effectiveness. The mobile application is distributed for
free through the Play Market and is designed for smartphones running the Android OS line.
The purpose of the development is to display in the application on the buyer's device first advertising
frequently purchased goods, and then the rest of the promotional goods. The mobile application has
passed load testing in real use by customers conditions of the retail network.